arXiv 2606.231262026-06-23cs.CV

MambaADv2: 面向无监督异常检测的进化型对偶增强状态空间模型

MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection

Zhejiang University（浙江大学）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究所）

Xiaobin Hu, Haoyang He, Bo Yin, Yu He, Lei Xie, Jiangning Zhang, Yu-Gang Jiang, Shuicheng Yan

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出MambaADv2框架，通过集成对偶增强状态空间模块和混合状态空间块，结合线性递归与并行矩阵计算，实现高效全局依赖与局部表示建模，提升多类无监督异常检测性能。

摘要：

尽管近期异常检测的进展展示了基于CNN和Transformer的方法的有效性，但这些架构存在固有限制：CNN难以捕捉长距离依赖，而Transformer则面临二次计算复杂度。因此，基于Mamba的架构引起了广泛关注，因为它们成功地将优越的长距离依赖建模与线性计算复杂度相结合。通过批判性地重新思考Mamba系列1-3的结构演化，本文提出了MambaADv2，一个专为多类无监督异常检测设计的框架。MambaADv2包含一个预训练编码器和一个受Mamba启发的解码器，并在多个尺度上配备了对偶增强状态空间（DSS）模块。所提出的DSS模块通过集成并行级联混合状态空间（HSS）块和频率增强卷积操作，有效建模全局依赖和局部表示。混合状态空间（HSS）块的结构遵循基于SSD的Mamba系列，并融入Mamba3风格的位置感知状态空间建模，利用线性递归和并行矩阵公式的双重计算路径来建模局部连续性和全局上下文比较，从而更好地服务于精确重建正常表示同时放大异常偏差的核心异常检测目标。此外，我们提出了一种语义自适应渐进扫描策略，该策略沿特征金字塔递减扫描复杂度。

英文摘要：

While recent advancements in anomaly detection have demonstrated the efficacy of CNN- and Transformer-based approaches, these architectures face inherent limitations: CNNs struggle to capture long-range dependencies, whereas Transformers suffer from quadratic computational complexity. Consequently, Mamba-based architectures have attracted considerable attention, as they successfully combine superior long-range dependency modeling with linear computational complexity. By critically rethinking the structural evolution across the Mamba lineage 1-3 series, this paper proposes MambaADv2, a framework tailored for multi-class unsupervised anomaly detection. MambaADv2 comprises a pre-trained encoder and a Mamba-inspired decoder, equipped with Duality-enhanced State Space (DSS) modules across multiple scales. The proposed DSS module effectively models both global dependencies and local representations by integrating parallel-cascaded Hybrid State Space (HSS) blocks and frequency-enhanced convolution operations. The structure of the Hybrid State Space (HSS) block is tailored by following the SSD-based Mamba lineage and incorporating Mamba3-style position-aware state-space modeling, leveraging the dual computational paths of linear recurrence and parallel matrix formulation to model local continuity and global contextual comparison, thereby better serving the core anomaly detection objective of precisely reconstructing normal representations while magnifying anomalous deviations. Additionally, we propose a semantics-adaptive progressive scanning strategy that decays scanning complexity along the feature pyramid.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。